• Convince you to consider investing in large scale lab based performance analysis.
• Dig into some data.

Why is consistently interactive so multi-modal?

• Find Chrome and Website bugs based on new insight.
• Understand Page Load performance at scale.
• Identify weaknesses in our metrics.

• Load the Alexa top 10k on Nexus 5's.
• Simulate 3G network.
• Both warm & cold Page loads.
• Reasonably detailed main thread attribution.

What's with the weird dip in warm wall clock time?

• Issue.
• Some low hanging fruit:

Slice Title: Total self time in ms across top 10k pages
LocalFrameView::performLayout :  77859682.3385
TaskQueueManager::RunTask :  45631790.6605
Document::recalcStyle :  42088368.0356
Document::rebuildLayoutTree :  23380524.8535
LocalFrameView::prePaint :  22698465.596
WebURLLoaderImpl::loadSynchronously :  19509370.842
ProxyMain::BeginMainFrame::commit :  16127438.698

• We need some better ways to keep trace event renaming from breaking metrics.
• Contribute by adding your slices to the user friendly category driver..

• blocked_on_network should split out by type of resource.
• Can script_execute be split out via runtimeCallStats?
• Filter out 404s - maybe pick a better pageset?
• ???

• Label sites by framework.
• Gather memory data as well.
• Do the same thing, but for input.